PhD student at University of Toronto, supervised by Steven Waslander. We're interested in perception and decision-making algorithms that can adapt to open-world settings.
Letian Wang
Hi there! I'm a Ph.D. student at the University of Toronto, where I am so fortunate to be supervised by the brilliant Prof. Steven Waslander (Nicest Steve Ever!) in the Toronto Robotics and AI Lab. I'm affiliated with Vector Institute founded by Prof. Geoffrey Hinton. Previously, I was also fortunate to do research with/at:
My research interests lie in the intersection between autonomous driving, robotics, machine learning, computer vision, with special interest in 3D vision, multimodal agent, end-to-end driving, human-robot interaction, and behavior forecasting. I recently focus on developping generalizable decision-making and scalable perception systems, powered by foundation models and learning paradigm that scales well with data, viewing safety as the most precious priority.
I have authored 1 book, was the winner of 2022 CARLA autonomous driving challenge, and won the best paper award honorable mention at RA-L 2021, first prize in the National Challenge Cup 2017 (全国挑战杯一等奖, known as the Olympics of sci./tech. for university students in China), and co-founded a start-up in industrial UAVs.
G. Scholar LinkedIn Twitter
I am always happy to chat or collaborate with people with different backgrounds. If you are interested in my work, please feel free to reach out!
I'm looking for internship in 2025, and exploring post-doc, industrial positions, and academic position for 2026.
letianwang0 at gmail dot com
Some recent highlights from our research:
2025
Three proposals selected as Qualcom Fellowship Finalist
SmartPretrain accepted to ICLR, early exploration of scaling laws in motion prediction!
Check out DistillNeRF, perceiving/reconstructing the 3D driving world without any labels or per-scene training!
Passed my PhD qualification, officially a PhD candidate now
LmDrive and SmartRefine get accepted to CVPR
I start my internship in NVIDIA Research Autonomous Vehicle
Research Group.
Invited by zdjszx.com to give a public
course on Intelligent/Generalizable Decision Making in Dense Environment.
Our ASAP-RL on efficient reinforcement learning for
autonomous driving is accepted by RSS.
Our ReasonNet
on end-to-end driving with temporal and global reasoning is accepted by CVPR.
Our book on Social Interactions for Autonomous
Driving is published by Foundations and Trends in Robotics.
One paper received the Best Paper Award - Honorable Mention of RA-L 2021.
National Scholarship, Beihang University
2018
May-Fourth Medal, highest honor for undergraduate at Beihang university, 10 people each year2017
First prize in National Challenge Cup (全国挑战杯一等奖, known as Sci./Tech. Olympics among universities in China)
Co-founding a start-up providing industrial UAVs for arial mapping and inspection.
![[Memory]](images/award.jpg){kind=link}